ux

ux is a skill for Claude Code, Codex from MountainUnicorn/add. It costs 26 tokens per session (2,081 once invoked), scanned A, original, MIT.

A guided design step for planning a feature's user interface and user experience before coding begins. It creates a design document that must be approved before planning and test-driven development continue.

In plain words
What is it for?
Reviewing screens, interactions, and other user-facing parts of a feature, including designs brought in from Figma.
Why use it?
It helps catch incorrect interface decisions before implementation work is spent on them.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/mountainunicorn/add/ux
Any agent
npx skills add MountainUnicorn/add --skill ux
Clone the repo
git clone --depth 1 https://github.com/MountainUnicorn/add

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ux

README.md
[![agentmods](https://agentmods.dev/badge/skills/mountainunicorn/add/ux.svg)](https://agentmods.dev/skills/mountainunicorn/add/ux)
Your own site
<a href="https://agentmods.dev/skills/mountainunicorn/add/ux"><img src="https://agentmods.dev/badge/skills/mountainunicorn/add/ux.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,081 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.02081
Opus 5 $0.00013 $0.01040
Sonnet 5 $0.00005 $0.00416
Haiku 4.5 $0.00003 $0.00208

Measured 3d ago against content hash 0bfa1b65df46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

core/skills/ux/SKILL.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADD UX Command v{{VERSION}}

Iterate on UI/UX design for a feature before implementation begins. Produces a signed-off design artifact that gates /add:plan and /add:tdd-cycle. Prevents token burn from building the wrong UI.

Pre-Flight

  1. Read .add/config.json to understand project context and maturity level
  2. If spec-file argument is provided, read it. Otherwise, list specs in specs/ and ask which feature to design
  3. Verify the spec exists and has a UI component (Q8 answered, or acceptance criteria mention UI states)
    • If no UI component is detectable, confirm with the human: "This spec doesn't appear to have a UI — do you still want to run a UX iteration?"
  4. Check if a UI artifact already exists at specs/ux/{feature-slug}-ux.md
    • If it does, and it's marked Status: APPROVED, ask: "This feature already has a signed-off design. Start over or review the existing one?"

Phase 1: Design Source

Determine where the design will come from.

Step 1: Check for Figma MCP

Attempt to detect whether a Figma MCP tool is available in the current session.

If --figma argument was provided OR Figma MCP is available:

Figma integration detected.

Options:
  A) Provide a Figma file URL or frame ID to start from an existing design
  B) Skip Figma and generate wireframes from scratch

If the human provides a Figma link:

  • Use the Figma MCP to read the frame(s)
  • Summarize what was found: screen names, key components, flow structure
  • Note: Figma MCP is read-only — changes happen in conversation, not in Figma itself
  • Proceed to Phase 2 with the Figma content as the starting point

If no Figma MCP and no --figma argument:

  • Skip Figma detection silently
  • Proceed directly to wireframe generation in Phase 2

Phase 2: UX Iteration Loop

This phase is a conversation loop. Repeat until the human approves the design or explicitly exits.

Step 1: Understand the UI Requirements

Before generating anything, ask focused questions to understand what needs to be designed. Keep it tight — 3-5 questions max.

Read the full file on GitHub · 256 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 256 lines · 26 tokens per session scan A 0bfa1b65df46

Subscribe to this mod's changes

ux is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 2,081 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.